Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    titles and roles associated with authority and positions of power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roud
    -0.16
    cmc
    -0.16
     éĻIJ
    -0.15
    linger
    -0.15
    endencies
    -0.14
    agal
    -0.14
    tid
    -0.14
    éĤ
    -0.14
    ancel
    -0.14
    olie
    -0.14
    POSITIVE LOGITS
     called
    0.18
    652
    0.18
     apt
    0.17
    lege
    0.16
     “
    0.15
     langu
    0.15
    ãĤīãģĦ
    0.14
    ãĤ·ãĤ¢
    0.14
     "
    0.14
    (s
    0.14
    Act Density 0.420%

    No Known Activations